Leo Zang
@LeoTZ03
Protein Designer | Share Reading Notes (AI+Protein/RNA/DNA) | Incoming PhD student @harvardmed @DeboraMarksLab | Hosting @ml4proteins
Collection of Papers and Posts leozang.com/Paper-Collecti…
Whoa
5 months from funding to shipping our first frontier model. Latent-X achieves state-of-the-art hit rates for macrocycles and mini-binders, with picomolar binding affinities — a breakthrough in de novo protein binder design. Available now on our no-code platform!
🎲 Our paper on the genetics, energetics, and allostery in proteins with randomized cores and surfaces is out today @ScienceMagazine! 🧬 By charting a protein’s sequence universe, we could rationalize which versions were kept through evolution – and why many stable ones were not.
The Dayhoff Atlas dramatically expands the scale and diversity of publicly available protein data by providing the largest open dataset of natural proteins to date, GigaRef, and a first-in-class, large-scale dataset of synthetic proteins, BackboneRef.
Apply for the AITHYRA-CeMM International PhD Program! 15-20 fully funded PhD fellowships available in Vienna in AI/ML and Life Sciences Deadline for applications: 10 September 2025 apply.cemm.at
Aithyra Opening Symposium "AI for Life Science" with Nobel Laureate Frances Arnold as keynote speaker in addition to an outstanding line up of speakers on a variety of topics across biological scales and data modalities. Registration is now open at lnkd.in/dkJJCmqx
Excited to host @pranamanam next week for our career scientist series(which his prev student @LeoTZ03 helped start when he joined the ML4PE team💪🏼)Getting to see the lab’s work the past yr at Duke, I am confident they are up to cool things in the field, ya won’t wanna miss this✨
Next Wed (7/30) at 4PM ET, please join us for an exciting talk from @pranamanam about his research! Sign up on our website for zoom links!
Our online book Physics-Based Simulation v1.0.2 is live! phys-sim-book.github.io New in this update: ABD, modal reduction, MPM, PBD, and linear solvers! Huge thanks to all the amazing contributors who made this happen!
The biggest challenge for AI in biology isn't just models, it's the data used to train them. Standard biological data isn't built for AI. To unlock generative AI for drug discovery, we must rethink how we generate and capture data. 1/
Evo 2 update: new dependency versions (torch, transformer engine, flash attn) and a docker option mean it should be easy to setup without needing to compile locally. Happy ATGC-ing! github.com/ArcInstitute/e…
Next Wed (7/30) at 4PM ET, please join us for an exciting talk from @pranamanam about his research! Sign up on our website for zoom links!
Starting with macrocycles and mini-binders, expanding to nanobodies and more. Our mission: make biology programmable to make drug design instantaneous. Join early access: platform.latentlabs.com Technical report: tinyurl.com/latent-X Technical details:…
Our study where we develop EvoBind2: Design of linear and cyclic peptide binders from protein sequence information is now published! nature.com/articles/s4200…
Yes. Writing is not a second thing that happens after thinking. The act of writing is an act of thinking. Writing *is* thinking. Students, academics, and anyone else who outsources their writing to LLMs will find their screens full of words and their minds emptied of thought.
reprogramming cells with transcription factors is our most expressive tool for engineering cell state traditionally, we found TFs by ~guesswork @icmlconf we're sharing @newlimit's SOTA AI models that can design reprogramming payloads by building on molecular foundation models
Come see how to shrink protein sequences with diffusion at our talk tomorrow morning!!!
Best Paper Award Winners: @setlur_amrith, @AlanNawzadAmin, @wanqiao_xu, @EvZisselman
Excited to share: “Learning Diffusion Models with Flexible Representation Guidance” With my amazing coauthors @zhuci19, @sharut_gupta, @zy27962986, @StefanieJegelka, @stats_stephen, Tommi Jaakkola Paper: arxiv.org/pdf/2507.08980 Code: github.com/ChenyuWang-Mon…
Protenix-Mini: Efficient Structure Predictor via Compact Architecture, Few-Step Diffusion and Switchable pLM “1) Multi-step AF3 sampler is replaced by a few-step ODE sampler, significantly reducing computational overhead for the diffusion module part during inference; 2) In the…
Next Wed (7/23) at 4PM ET, Professor Possu Huang @PossuHuangLab will be giving a talk about his research! Sign up on our website for zoom links!
Hybrid explicit-latent flows are the new foundation models for protein structures. La-Proteina shows that one network can design 800-residue, all-atom structures and sequences, then perform well at motif scaffolding. Read more: nvda.ws/4nOjBSL